Match!
Matthew R. O'Shaughnessy
Georgia Institute of Technology
Filter (signal processing)Bayesian inferenceHyperpriorEmbeddingMarginal likelihood
2Publications
1H-index
2Citations
What is this?
Publications 4
Newest
Many signal processing applications require estimation of time-varying sparse signals, potentially with the knowledge of an imperfect dynamics model. In this paper, we propose an algorithm for dynamic filtering of time-varying sparse signals based on the sparse Bayesian learning (SBL) framework. The key idea underlying the algorithm, termed SBL-DF, is the incorporation of a signal prediction generated from a dynamics model and estimates of previous time steps into the hyperpriors of the SBL prob...
#1Gregory Canal (Georgia Institute of Technology)H-Index: 1
#2Matthew R. O'Shaughnessy (Georgia Institute of Technology)H-Index: 1
Last. Mark A. Davenport (Georgia Institute of Technology)H-Index: 29
view all 4 authors...
Source
#1Matthew R. O'Shaughnessy (Georgia Institute of Technology)H-Index: 1
#2Mark A. Davenport (Georgia Institute of Technology)H-Index: 29
Last. Christopher J. Rozell (Georgia Institute of Technology)H-Index: 19
view all 3 authors...
Source
#1Matthew R. O'Shaughnessy (Georgia Institute of Technology)H-Index: 1
#2Mark A. Davenport (Georgia Institute of Technology)H-Index: 29
Suppose that we wish to determine an embedding of points given only paired comparisons of the form “user x prefers item q i to item q j .” Such observations arise in a variety of contexts, including applications such as recommendation systems, targeted advertisement, and psychological studies. In this paper we first present an optimization-based framework for localizing new users and items when an existing embedding is known. We demonstrate that user localization can be formulated as a simple co...
2 CitationsSource
1